A lane changing method and device, vehicle and storage medium

Abstract

The application discloses a lane changing method and device, a vehicle and a storage medium. The method comprises the following steps: determining a lane changing trajectory control parameter of a current vehicle, generating at least one candidate lane changing trajectory according to a current driving position of the current vehicle and the lane changing trajectory control parameter, acquiring a predicted driving trajectory of a lane changing obstacle of the current vehicle, determining a lane changing time window corresponding to each candidate lane changing trajectory according to each candidate lane changing trajectory and the predicted driving trajectory, determining a target lane changing trajectory from the at least one candidate lane changing trajectory according to the lane changing time window corresponding to each candidate lane changing trajectory, and performing a lane changing operation in the lane changing time window of the target lane changing trajectory. The technical scheme of the application can solve the problem in the prior art that automatic lane changing is only started when the surrounding environment is absolutely safe, realize that there is more possibility of starting automatic lane changing in a complex traffic scene, and improve the lane changing probability of automatic lane changing.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a lane-changing method, device, vehicle, and storage medium. Background Technology

[0002] In autonomous driving technology, determining the appropriate lane-changing time and trajectory is crucial so that vehicles in autonomous driving mode can automatically change lanes according to the lane-changing trajectory within the specified time.

[0003] In existing technologies, automatic lane changing algorithms are relatively simple in design. Their core idea is to activate lane changing only when the surrounding environment is absolutely safe. However, the conditions for absolute safety are usually set very conservatively, resulting in overly stringent conditions for activating lane changing. Therefore, existing automatic lane changing algorithms can usually only be used in scenarios with relatively simple traffic environments.

[0004] However, due to the highly complex nature of real-world traffic environments, the probability of achieving automatic lane changing using existing algorithms is very low, meaning their applicability is relatively poor. Furthermore, in complex traffic scenarios, such as urban traffic, existing automatic lane changing algorithms are less likely to activate automatic lane changing mode due to the complex surrounding environment or numerous obstacles. Summary of the Invention

[0005] This invention provides a lane-changing method, device, vehicle, and storage medium to solve the problem in the prior art that automatic lane changing is only activated when the surrounding environment is absolutely safe. It enables more possibilities for activating automatic lane changing in complex traffic scenarios and can improve the lane-changing probability of automatic lane changing.

[0006] According to one aspect of the present invention, a lane-changing method is provided, the method comprising:

[0007] Determine the lane-changing trajectory control parameters for the current vehicle, and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters;

[0008] Obtain the predicted trajectory of the current vehicle in the lane-changing obstacle;

[0009] The lane-changing time window corresponding to each candidate lane-changing trajectory is determined based on each candidate lane-changing trajectory and the predicted driving trajectory;

[0010] The target lane change trajectory is determined from at least one candidate lane change trajectory based on the lane change time window corresponding to each candidate lane change trajectory.

[0011] Perform the lane change operation within the lane change time window of the target lane change trajectory.

[0012] According to another aspect of the present invention, a lane-changing device is provided, the device comprising:

[0013] The first generation module is used to determine the lane-changing trajectory control parameters of the current vehicle and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters.

[0014] The prediction module is used to obtain the predicted driving trajectory of the current vehicle in the lane-changing obstacle;

[0015] The window determination module is used to determine the lane change time window corresponding to each candidate lane change trajectory based on each candidate lane change trajectory and the predicted driving trajectory;

[0016] The second generation module is used to determine the target lane change trajectory from at least one candidate lane change trajectory based on the lane change time window corresponding to each candidate lane change trajectory.

[0017] The execution module is used to perform lane change operations within the lane change time window of the target lane change trajectory.

[0018] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the lane-changing method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the lane-switching method of any embodiment of the present invention.

[0023] The lane-changing method provided by this invention first generates candidate lane-changing trajectories based on the current vehicle's lane-changing trajectory control parameters and current driving position; it then obtains the predicted driving trajectory of lane-changing obstacles for the current vehicle, and determines the lane-changing time window corresponding to each candidate lane-changing trajectory based on each candidate lane-changing trajectory and the predicted driving trajectory; after determining the lane-changing time window corresponding to each candidate lane-changing trajectory, it determines the target lane-changing trajectory from at least one candidate lane-changing trajectory based on the lane-changing time window corresponding to each candidate lane-changing trajectory, and performs the lane-changing operation according to the lane-changing time window of the target lane-changing trajectory. In the above technical solution, on the one hand, by using lane-changing trajectory control parameters and the current vehicle's current driving position to generate at least one candidate lane-changing trajectory, multiple lane-changing trajectories are increased, thereby increasing the probability of selecting a suitable lane-changing trajectory subsequently. On the other hand, by predicting the trajectory of lane-changing obstacles, the problem of automatic lane changing only being activated when the surrounding environment is absolutely safe in the prior art is solved, and the possibility of activating automatic lane changing is increased by predicting the trajectory of lane-changing obstacles around the current vehicle. On the other hand, by determining the possibility of collision between candidate lane-changing trajectories and predicted driving trajectories, it ensures that a lane-changing trajectory with a safe lane-changing time window can be found from the candidate trajectories under complex traffic conditions, thereby improving the lane-changing probability and applicability of the automatic lane-changing method to a certain extent. Furthermore, by filtering out the target lane-changing trajectory from the candidate trajectories and executing the lane-changing operation according to the target lane-changing trajectory's lane-changing time window, it is possible to determine the target lane-changing trajectory and lane-changing time window and perform the vehicle's lane-changing operation even when the surrounding environment is not necessarily completely safe.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A schematic flowchart of the lane-changing method provided by the present invention;

[0027] Figure 2 Another schematic diagram of the lane-changing method provided by the present invention;

[0028] Figure 3 Example diagram of candidate lane change trajectory generation provided by the present invention;

[0029] Figure 4 This is a schematic diagram of the lane-changing device provided by the present invention;

[0030] Figure 5 This is a structural schematic diagram of the vehicle provided by the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," "original," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Figure 1 This is a schematic flowchart of a lane-changing method provided by the present invention. This embodiment is applicable to vehicles in autonomous driving mode that need to change lanes during driving. The method can be executed by a lane-changing device, which can be implemented in hardware and / or software and can be configured in the vehicle. Figure 1 As shown, the method includes:

[0034] S101. Determine the lane-changing trajectory control parameters of the current vehicle, and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters.

[0035] Among them, the lane-changing trajectory control parameters are the relevant parameters used to calculate the lane-changing trajectory. In this embodiment, the lane-changing trajectory control parameters can be parameters such as lane-changing trajectory duration, number of lane-changing trajectory points, and lane-changing speed.

[0036] Specifically, when a lane change is required during the current vehicle's operation, the lane change trajectory control parameters can be determined. For example, since these parameters are used to calculate the lane change trajectory, generating a lane change trajectory can include control parameters such as the lane change trajectory duration, the number of lane change trajectory points, and the lane change speed. Optionally, the lane change trajectory duration and the number of lane change trajectory points can be determined by the vehicle's computing power, or a suitable range for the duration and number of points can be determined based on prior experiments and trials. Optionally, the lane change speed can be determined based on the user's perception of the vehicle while it is in motion, resulting in a comfortable speed. This speed can include a comfortable driving speed when the vehicle is traveling at a constant speed, as well as comfortable acceleration and deceleration during acceleration and deceleration. Furthermore, the lane change speed can be determined based on user feedback during experiments or trials, or by measuring acceleration using an accelerometer and combining it with methods for calculating comfortable acceleration.

[0037] Specifically, after determining the lane-changing trajectory control parameters of the current vehicle, the current driving position of the vehicle can be determined using positioning sensors or perception sensors carried by the vehicle itself. At least one candidate lane-changing trajectory is then generated based on the current driving position of the vehicle and the lane-changing trajectory parameters.

[0038] For example, in one implementation, based on the current vehicle's current position and speed, the vehicle's position *s* and time *t0* when the vehicle reaches a set lane-changing speed are predicted, and *s* and *t0* are used as the starting point and starting time of the lane-changing trajectory. The lane-changing time interval between each lane-changing trajectory point is determined based on the number of lane-changing trajectory points *n* and the trajectory duration *t*. Starting from the starting point of the lane-changing trajectory, the next lane-changing trajectory point is determined according to different lane-changing speeds and time intervals until all lane-changing trajectory points are obtained, and the route connecting all lane-changing trajectory points is used as a candidate lane-changing trajectory. In another implementation, the current vehicle's current position is used as the starting point *s*, and the time at the current position is used as the starting time *t0*. The time of each lane-changing trajectory point is determined based on the trajectory duration *t* and the number of lane-changing trajectory points *n*. That is, starting from *t0*, the time of each subsequent lane-changing trajectory point differs from the time of its predecessor by *t / n* time. After determining the time of each lane change trajectory point, the distance the current vehicle travels from the current lane change trajectory point to the next lane change trajectory point is determined using the same lane change speed. Based on the time and position of the current lane change trajectory point, the time and position of the next lane change trajectory point are determined, until all lane change trajectory points are obtained, and the route connecting all lane change trajectory points is used as a candidate lane change trajectory.

[0039] In this embodiment, at least one candidate lane-changing trajectory is generated using the lane-changing trajectory control parameters and the current driving position of the vehicle, thus increasing the number of lane-changing trajectories and increasing the probability of selecting a suitable lane-changing trajectory in the future.

[0040] S102. Obtain the predicted driving trajectory of the current vehicle in the lane-changing obstacle.

[0041] Among them, lane-changing obstacles refer to obstacles in the surrounding area that may affect the current vehicle's lane-changing when the vehicle is preparing to change lanes.

[0042] Specifically, during lane changing, there may be obstacles around the current vehicle that could affect its lane change. These could include vehicles in the same lane, vehicles in the target lane, or pedestrians preparing to enter the lane from the roadside. Therefore, it is necessary to predict the trajectory of these lane-changing obstacles.

[0043] For example, vehicle monitoring equipment can be used to determine whether there are lane-changing obstacles around the current vehicle that may affect the current vehicle's lane-changing. If so, object recognition and tracking technology can be used to identify and track the lane-changing obstacle and predict its trajectory.

[0044] In this embodiment, the problem that automatic lane changing is only activated when the surrounding environment is absolutely safe is solved by predicting the trajectory of lane-changing obstacles in the prior art. By predicting the trajectory of lane-changing obstacles around the current vehicle, the possibility of activating automatic lane changing is increased.

[0045] S103. Determine the lane change time window corresponding to each candidate lane change trajectory based on each candidate lane change trajectory and the predicted driving trajectory.

[0046] The lane-changing time window is a feasible time window for the current vehicle to perform an automatic lane change. In this embodiment, the lane-changing time window may include the lane-changing start time and the lane-changing end time. For example, the lane-changing time window can be represented as (t... S , t E ).

[0047] Specifically, upon obtaining the candidate lane-changing trajectory and the predicted driving trajectory, it can be determined whether each candidate lane-changing trajectory has a corresponding lane-changing time window. For example, it can be determined whether there exists a time period within each candidate lane-changing trajectory during which there is no risk of collision with the predicted driving trajectory when changing lanes; if such a time period exists, then that time period is the lane-changing time window; if not, it indicates that the candidate lane-changing trajectory does not meet the lane-changing requirements and should be discarded.

[0048] In this embodiment, by determining whether there is a possibility of collision between the candidate lane-changing trajectory and the predicted driving trajectory, it is ensured that a lane-changing trajectory with a safe lane-changing time window can be found from the candidate lane-changing trajectories under complex traffic conditions. This improves the lane-changing probability and applicability of the automatic lane-changing method to a certain extent.

[0049] S104. Determine the target lane change trajectory from at least one candidate lane change trajectory based on the lane change time window corresponding to each candidate lane change trajectory.

[0050] The target lane-changing trajectory is the lane-changing trajectory that is ultimately determined during the autonomous driving process.

[0051] Specifically, if more than one candidate lane-changing trajectory and its corresponding lane-changing time window can be determined based on the candidate lane-changing trajectory and the predicted driving trajectory, then the target lane-changing trajectory needs to be determined from at least one candidate lane-changing trajectory. For example, the target lane-changing trajectory can be determined based on the lane-changing time window corresponding to each candidate lane-changing trajectory. In one implementation, the candidate lane-changing trajectory corresponding to the lane-changing time window with the longest duration is selected as the target lane-changing trajectory. In another implementation, the candidate lane-changing trajectory corresponding to the lane-changing time window whose start time is closest to the current time is selected as the target lane-changing trajectory. Yet another implementation, the candidate lane-changing trajectory with the longest distance within the same lane-changing time window is selected as the target lane-changing trajectory.

[0052] S105. Perform a lane change operation within the lane change time window of the target lane change trajectory.

[0053] Specifically, once the target lane-changing trajectory is determined, the lane-changing operation can be performed according to the lane-changing time window of the target lane-changing trajectory.

[0054] In this embodiment, by selecting the target lane-changing trajectory from the candidate lane-changing trajectories and performing the lane-changing operation according to the lane-changing time window of the target lane-changing trajectory, it is possible to determine the target lane-changing trajectory and the lane-changing time window and realize the lane-changing operation of the vehicle even when the surrounding environment is not necessarily completely safe.

[0055] The lane-changing method provided by this invention first generates candidate lane-changing trajectories based on the current vehicle's lane-changing trajectory control parameters and current driving position; it then obtains the predicted driving trajectory of lane-changing obstacles for the current vehicle, and determines the lane-changing time window corresponding to each candidate lane-changing trajectory based on each candidate lane-changing trajectory and the predicted driving trajectory; after determining the lane-changing time window corresponding to each candidate lane-changing trajectory, it determines the target lane-changing trajectory from at least one candidate lane-changing trajectory based on the lane-changing time window corresponding to each candidate lane-changing trajectory, and performs the lane-changing operation according to the lane-changing time window of the target lane-changing trajectory. In the above technical solution, on the one hand, by using lane-changing trajectory control parameters and the current vehicle's current driving position to generate at least one candidate lane-changing trajectory, multiple lane-changing trajectories are increased, thereby increasing the probability of selecting a suitable lane-changing trajectory subsequently. On the other hand, by predicting the trajectory of lane-changing obstacles, the problem of automatic lane changing only being activated when the surrounding environment is absolutely safe in the prior art is solved, and the possibility of activating automatic lane changing is increased by predicting the trajectory of lane-changing obstacles around the current vehicle. On the other hand, by determining the possibility of collision between candidate lane-changing trajectories and predicted driving trajectories, it ensures that a lane-changing trajectory with a safe lane-changing time window can be found from the candidate trajectories under complex traffic conditions, thereby improving the lane-changing probability and applicability of the automatic lane-changing method to a certain extent. Furthermore, by filtering out the target lane-changing trajectory from the candidate trajectories and executing the lane-changing operation according to the target lane-changing trajectory's lane-changing time window, it is possible to determine the target lane-changing trajectory and lane-changing time window and perform the vehicle's lane-changing operation even when the surrounding environment is not necessarily completely safe.

[0056] Figure 2 This is another schematic flowchart of the lane-changing method provided by the present invention. Based on the above embodiments, this embodiment provides a detailed explanation of the steps for determining the lane-changing trajectory control parameters of the current vehicle, generating candidate lane-changing trajectories, determining the lane-changing time window corresponding to each candidate lane-changing trajectory based on the candidate lane-changing trajectories and the predicted driving trajectory, and determining the target lane-changing trajectory from at least one candidate lane-changing trajectory. For example... Figure 2 As shown, the method includes:

[0057] S201. Determine the current vehicle's comfort acceleration, comfort deceleration, and comfort driving speed based on user feedback.

[0058] Here, comfort acceleration is the vehicle acceleration at which the user feels relatively comfortable during vehicle operation. Similarly, comfort deceleration is the vehicle deceleration at which the user feels relatively comfortable during vehicle operation. Comfortable driving speed is the vehicle speed at which the user feels relatively comfortable during vehicle operation. In this embodiment, the comfortable driving speed can be calculated from comfort acceleration and comfort deceleration, or it can be the driving speed at which the user feels relatively comfortable when the vehicle is traveling at a constant speed.

[0059] Specifically, before calculating the automatic lane-changing trajectory, it is necessary to determine the parameters used to generate the automatic lane-changing trajectory. These parameters include the current vehicle's comfort acceleration, comfort deceleration, and comfort speed.

[0060] For example, comfort acceleration, comfort deceleration, and comfort driving speed can be obtained as follows: In one implementation, during an experiment, when the driver controls the vehicle from inside the vehicle, or when the driver monitors the vehicle in autonomous driving mode from inside the vehicle, the acceleration, deceleration, and driving speed that the user feels most comfortable during acceleration, deceleration, and constant speed driving are recorded and used as comfort acceleration, comfort deceleration, and comfort driving speed, respectively. In another implementation, during actual driving, the acceleration, deceleration, and driving speed that the user feels most comfortable during vehicle acceleration, deceleration, and driving are recorded and used as comfort acceleration, comfort deceleration, and comfort driving speed. Furthermore, the comfort acceleration, comfort deceleration, and comfort driving speed can be continuously adjusted based on the user's experience during actual driving.

[0061] S202. Determine the lane-changing trajectory duration and the number of lane-changing trajectory points based on the current vehicle's computing power.

[0062] Specifically, before calculating the automatic lane-changing trajectory, the parameters used to generate the automatic lane-changing trajectory need to be determined. In addition to determining the comfort acceleration, comfort deceleration, and comfort speed, the lane-changing trajectory duration and the number of lane-changing trajectory points also need to be determined.

[0063] For example, the lane-changing trajectory duration and the number of lane-changing trajectory points can be obtained as follows. In one implementation, during actual driving, the appropriate lane-changing trajectory duration and the number of lane-changing trajectory points are determined based on the current vehicle's computing power. That is, if the current vehicle's computing power is weak, the lane-changing trajectory duration should be shorter and the number of lane-changing trajectory points fewer; if the current vehicle's computing power is strong, the lane-changing trajectory duration should be longer and the number of lane-changing trajectory points more. In another implementation, during the experiment, different lane-changing trajectory durations and the number of lane-changing trajectory points are selected based on the current vehicle's computing power. By continuously changing the lane-changing trajectory duration and the number of lane-changing trajectory points, a more suitable range for the lane-changing trajectory duration and the number of lane-changing trajectory points is determined, and the lane-changing trajectory duration and the number of lane-changing trajectory points are determined each time within this suitable range during actual driving.

[0064] S203. Comfort acceleration, comfort deceleration, comfort driving speed, lane change trajectory duration, and number of lane change trajectory points are used as lane change trajectory control parameters.

[0065] Specifically, after determining the current vehicle's comfort acceleration, comfort deceleration, and comfort driving speed based on user feedback, and determining the lane-changing trajectory duration and the number of lane-changing trajectory points based on the current vehicle's computing capabilities, the comfort acceleration, comfort deceleration, comfort driving speed, lane-changing trajectory duration, and the number of lane-changing trajectory points can be used as lane-changing trajectory control parameters.

[0066] In this embodiment, before calculating the automatic lane-changing trajectory, parameters for generating the automatic lane-changing trajectory are determined, namely lane-changing trajectory control parameters, which provide a calculation basis for the vehicle to generate a more suitable and comfortable candidate lane-changing trajectory based on its own computing capabilities when generating the automatic lane-changing trajectory.

[0067] S204. Determine the time information of the trajectory start point based on the current time, and determine the location information of the trajectory start point based on the current driving position.

[0068] Specifically, the starting point of the lane-changing trajectory can be determined based on the current time, and the starting point of the lane-changing trajectory can be determined based on the current vehicle's position.

[0069] For example, the time information of the trajectory starting point can be determined in the following ways. In one implementation, once the current time is determined, it can be used as the time information of the trajectory starting point. In another implementation, once the current time is determined, based on the current vehicle's speed and its environment, the time after traveling at the current vehicle's speed for a certain period of time is determined, and this time is used as the time information of the trajectory starting point. For example, if the current time is 11:00:00, the current vehicle's speed is 60 km / h, and the time after traveling for 3 seconds is 11:00:50, then the time information of the trajectory starting point is 11:00:50.

[0070] For example, the location information of the trajectory starting point can be determined in the following ways. In one implementation, the current vehicle's position can be directly determined as the location information of the lane-changing trajectory starting point. That is, the location of the lane-changing trajectory starting point is the current vehicle's position. In another implementation, the vehicle's travel distance is determined based on the current vehicle's speed and the time information of the trajectory starting point, and the location information of the trajectory starting point is determined using the current vehicle's position and travel distance. For example, if the current vehicle's position is s0, and the vehicle's travel distance is determined as v0t0 based on the current vehicle's speed v0 and the time information t0 of the trajectory starting point, then the location information of the trajectory starting point is s0+v0t0 or s0-v0t0. The location information of the trajectory starting point, s0+v0t0 or s0-v0t0, is determined according to the vehicle's specific travel direction.

[0071] S205. Obtain the time information of the previous candidate trajectory point.

[0072] The candidate trajectory points include the current candidate trajectory point and the previous candidate trajectory point, where the previous candidate trajectory point is the one preceding the current candidate trajectory point. In this embodiment, the previous candidate trajectory point may be the trajectory starting point, or it may not be the trajectory starting point. That is, in the entire candidate trajectory, there is always a previous candidate trajectory point that is the trajectory starting point.

[0073] Specifically, before determining each candidate trajectory point, it is necessary to obtain the time information of the previous candidate trajectory point in order to facilitate the subsequent calculation of the current trajectory point.

[0074] S206. Determine the time interval between points based on the duration of the lane change trajectory and the number of lane change trajectory points.

[0075] Specifically, after determining the lane-changing trajectory duration and the number of lane-changing trajectory points based on the current vehicle's computing power, the time interval between each lane-changing trajectory point can be determined according to the appropriate lane-changing trajectory duration and the number of lane-changing trajectory points. For example, assuming the lane-changing trajectory duration is T and the number of lane-changing trajectory points is n, the time interval between each lane-changing trajectory point can be determined to be T / n.

[0076] S207. Determine the time information of the current candidate trajectory point based on the time information of the previous candidate trajectory point and the time interval between points.

[0077] Specifically, after obtaining the time information and inter-point time interval of the previous candidate trajectory point, the time information of the current candidate trajectory point can be determined. For example, in one implementation, assuming the previous candidate trajectory point is the trajectory starting point, the time information t1 of the current candidate trajectory point can be determined using the time information t0 of the trajectory starting point and the inter-point time interval T / n, which is t0 = t0 + T / n. In another implementation, assuming the previous candidate trajectory point is not the trajectory starting point, the time information t1 of the previous candidate trajectory point can be determined using the time information t0 of the previous candidate trajectory point. i The time information t of the current candidate trajectory point is determined by the time interval T / n between points. i+1 =t i +T / n.

[0078] In this embodiment, the time information of each candidate trajectory point can be obtained by determining the time information of the trajectory start point, the duration of the lane change trajectory, and the number of lane change trajectory points.

[0079] S208. Determine the first driving distance obtained by driving according to the comfort acceleration and the time information of the current candidate trajectory point, and determine the first position information of the current candidate trajectory point according to the position information of the previous candidate trajectory point and the first driving distance.

[0080] Specifically, the first distance traveled by the vehicle from the previous candidate trajectory point to the current candidate trajectory point can be determined based on the comfort acceleration and the time information of the current candidate trajectory point. After obtaining the first distance, the first position information of the current candidate trajectory point can be determined based on the position information of the previous candidate trajectory point. For example, assuming that the first distance traveled by the vehicle from the previous candidate trajectory point to the current candidate trajectory point is S1 based on the comfort acceleration and the time information of the current candidate trajectory point, and the position information of the previous candidate trajectory point is s... i Then the first position information of the current candidate trajectory point is s. i +S1.

[0081] S209. Determine the second travel distance obtained by traveling according to the comfort deceleration and the time information of the current candidate trajectory point, and determine the second position information of the current candidate trajectory point based on the position information of the previous candidate trajectory point and the second travel distance.

[0082] Specifically, in addition to calculating the position information of the current candidate trajectory point according to method S208, the second travel distance from the previous candidate trajectory point to the current candidate trajectory point can be determined based on the comfort deceleration and the time information of the current candidate trajectory point. After obtaining the second travel distance, the second position information of the current candidate trajectory point can be determined based on the position information of the previous candidate trajectory point. For example, assuming that the second travel distance from the previous candidate trajectory point to the current candidate trajectory point is determined to be S2 based on the comfort deceleration and the time information of the current candidate trajectory point, and the position information of the previous candidate trajectory point is s... i Then the second position information of the current candidate trajectory point is s. i +S2.

[0083] S210. Determine the third driving distance obtained by driving at a comfortable driving speed and the time information of the current candidate trajectory point, and determine the third position information of the current candidate trajectory point based on the position information of the previous candidate trajectory point and the third driving distance.

[0084] Specifically, in addition to calculating the position information of the current candidate trajectory point according to methods S208 and S209, the third travel distance from the previous candidate trajectory point to the current candidate trajectory point can also be determined based on the comfortable driving speed and the time information of the current candidate trajectory point. After obtaining the third travel distance, the third position information of the current candidate trajectory point can be determined based on the position information of the previous candidate trajectory point. For example, assuming that the third travel distance from the previous candidate trajectory point to the current candidate trajectory point is determined to be S3 based on the comfortable deceleration and the time information of the current candidate trajectory point, and the position information of the previous candidate trajectory point is s... i Then the third position information of the current candidate trajectory point is s. i +S3.

[0085] S211. Generate at least one candidate lane-changing trajectory based on the time and location information of the trajectory starting point, as well as the time, first, second, and third location information of the candidate trajectory points.

[0086] Specifically, starting from the trajectory starting point, and using the trajectory starting point as the first previous candidate trajectory point, the time and position information of the current candidate trajectory point can be obtained by following one of the steps, such as S208, S209, or S210. Then, for each current candidate trajectory point with known time and position information, as the previous candidate trajectory point, all lane-changing trajectory points can be obtained by following one of the steps, such as S208, S209, or S210, and a candidate lane-changing trajectory composed of all lane-changing trajectory points can be generated.

[0087] For example, the time and position information of each lane-changing trajectory point are represented in coordinate form, such as (time information, position information). The trajectory starting point is taken as the first previous candidate trajectory point, and the time and position information of the trajectory starting point are (t0, s0). In one implementation, the time and position information of the current candidate trajectory point are determined according to S208 (t1 = t0 + T / n, s1 = s1 + S1); in another implementation, the time and position information of the current candidate trajectory point are determined according to S209 (t1 = t0 + T / n, s1 = s1 + S2); and in yet another implementation, the time and position information of the current candidate trajectory point are determined according to S210 (t1 = t0 + T / n, s1 = s1 + S3). At this point, the current candidate trajectory point can be used as the previous candidate trajectory point, and the time and position information of the new current candidate trajectory point can be obtained according to the above method until at least one candidate lane-changing trajectory is generated.

[0088] For example, such as Figure 3 As shown. Figure 3 An example diagram illustrating the generation of candidate lane-changing trajectories provided by this invention. Figure 3 In this process, starting from point P0, trajectory Tr1 is a candidate lane-changing trajectory. Trajectory Tr1 starts from P0 and is calculated using the method described above. Point P0 is taken as the previous candidate trajectory point, and the time and position information of point P11 can be determined based on the time and position information of point P0. After obtaining the time and position information of point P11, point P11 is taken as the previous candidate trajectory point, and point P12 is obtained by following one of the steps S208, S209, or S210. Similarly, points P13, P14, P15, P16, P17, and P18 can be obtained by different selections. After obtaining all trajectory points, P0-P11-P12-P13-P14-P15-P16-P17-P18 can be considered as a candidate lane-changing trajectory. Similarly, starting from point P0, following one of the steps S208, S209, or S210, the following can also be obtained: Figure 3 Candidate lane-changing trajectories for trajectory Tr2, i.e., P0-P21-P22-P23-P24-P25-P26-P27.

[0089] It is worth noting that in this embodiment, S208, S209, and S210 are three parallel optional schemes. After executing S207, one of S208, S209, or S210 can be selected for execution. That is, the position information of each current candidate trajectory point can be calculated according to one of S208, S209, or S210 until at least one candidate lane-changing trajectory is generated.

[0090] In this embodiment, each current candidate trajectory point can determine a first driving distance, a second driving distance, or a third driving distance based on the comfort acceleration, comfort deceleration, or comfort driving speed and the time information of the current candidate trajectory point. Furthermore, based on the position information of the previous candidate trajectory point and the first, second, or third driving distance, the first, second, or third position information corresponding to the current candidate trajectory point can be determined. This enables the determination of different current candidate trajectory points according to comfort acceleration, comfort deceleration, or comfort driving speed and other parameters, thereby increasing the possibility of multiple lane-changing trajectories to a certain extent, so as to achieve a greater probability of selecting a suitable lane-changing trajectory in the future.

[0091] S212. Identify obstacles in the current lane and obstacles in the lane changing lane.

[0092] In this context, obstacles in the current lane refer to obstacles in the same lane as the current vehicle. Obstacles in the lane-changing lane refer to obstacles in the target lane of the current vehicle. Furthermore, in this embodiment, if an obstacle from another lane moves to the current lane or the target lane-changing lane during a subsequent lane-changing process, that obstacle will also be updated to an obstacle in the current lane or the target lane-changing lane.

[0093] Specifically, the vehicle's onboard camera can be used to identify obstacles in the current lane and in the lane to change lanes. Alternatively, the vehicle's built-in sensors can be used to determine if obstacles exist around the vehicle.

[0094] S213. Identify obstacles in the current lane and obstacles in the lane changing lane as lane changing obstacles.

[0095] Specifically, since obstacles in other lanes do not affect the current vehicle's lane change, only obstacles in the current lane and obstacles in the lane to be changed are identified as lane change obstacles.

[0096] S214. Obtain the predicted driving trajectory of lane-changing obstacles.

[0097] Specifically, a predictive model in the vehicle can be used to predict the trajectory of lane-changing obstacles. Simultaneously, the predicted trajectory duration should correspond to each candidate lane-changing trajectory, providing a basis for subsequently using the predicted trajectory and candidate lane-changing trajectories to determine whether there is a possibility of collision with the lane-changing obstacle during the current vehicle's lane-changing process according to the candidate lane-changing trajectory.

[0098] S215. The time window that satisfies the first and second conditions is determined as the lane-changing time window corresponding to each candidate lane-changing trajectory.

[0099] The first condition is that there is no collision between the candidate lane-changing trajectory and the predicted driving trajectory within the lane-changing time window; the second condition is that the length of the lane-changing time window exceeds the preset duration. The lane-changing time window includes the lane-changing start time and the lane-changing end time. The lane-changing time window is the time window from when the current vehicle starts executing the lane-changing operation at the start time to when the lane-changing operation is completed at the end time.

[0100] Specifically, the candidate lane-changing trajectory and the predicted driving trajectory are compared to determine whether there exists a lane-changing time window that allows the vehicle to begin changing lanes at the start time of the lane-changing time window and complete the lane-changing process without colliding with obstacles predicted by the predicted driving trajectory. The first condition is specifically used to identify candidate lane-changing trajectories that do not collide with the predicted driving trajectory within the lane-changing time window. The second condition is specifically used to determine whether the lane-changing time window satisfies the requirement that the current vehicle can completely execute the lane-changing process.

[0101] For example, suppose there are three candidate lane-changing trajectories. The first candidate lane-changing trajectory tr1 almost overlaps with the predicted driving trajectory, meaning there is no lane-changing time window for the current vehicle to travel along the candidate lane-changing trajectory without colliding with the predicted driving trajectory. Therefore, candidate lane-changing trajectory tr1 has no lane-changing window. The second candidate lane-changing trajectory tr2 has a lane-changing time window (T... S1 T E1 ), whose candidate lane-changing trajectory does not collide with the predicted driving trajectory. Among them, T S1 T is the start time of the lane change. E1 This is the lane change end time. However, due to the length T of the lane change time window... L1 =T E1 -T S1 The preset duration T has not been exceeded. P That is, the current vehicle starts from T S1 From this moment until T E1 Up to this point, due to the short time frame, it may not be sufficient for the current vehicle to change lanes normally. Therefore, the lane-changing time window for the second candidate lane-changing trajectory tr2 is only (T... S1 T E1Meanwhile, the second candidate lane-changing trajectory tr2 does not satisfy the lane-changing time windows corresponding to the first and second conditions. The third candidate lane-changing trajectory tr3 has two lane-changing time windows (T). S2 T E2 ) and (T S3 T E3 The candidate lane-changing trajectory does not collide with the predicted driving trajectory. Meanwhile, the length T of the lane-changing time window... L2 =T E2 -T S2 The preset duration T has not been exceeded. P T L3 =T E3 -T S3 Exceeding the preset duration T P Therefore, it can be determined that in (T) S3 T E3 Within the lane-changing time window (T), the current vehicle can be guaranteed to change lanes normally. Therefore, the time window (T) that satisfies the first and second conditions is... S3 T E3 ), which is the lane change time window corresponding to the candidate lane change trajectory.

[0102] S216. Obtain the determination result of the lane change time window corresponding to each candidate lane change trajectory.

[0103] The results include those with a corresponding lane-changing time window and those without a corresponding lane-changing time window.

[0104] Specifically, based on the results of the above steps, the determination result for the lane-changing time window corresponding to each candidate lane-changing trajectory can be obtained. For example, for the first candidate lane-changing trajectory tr1, the determination result is no corresponding lane-changing time window. For the second candidate lane-changing trajectory tr2, although there exists a lane-changing time window that satisfies the first condition, this lane-changing time window does not satisfy the second condition. Therefore, for the second candidate lane-changing trajectory tr2, the determination result is also no corresponding lane-changing time window. For the third candidate lane-changing trajectory tr3, there are two lane-changing time windows that satisfy the first condition, and (T... S3 T E3 The lane-changing time window of the third candidate lane-changing trajectory tr3 satisfies the second condition. Therefore, the determination result is that there is a corresponding lane-changing time window (T). S3 T E3 ).

[0105] S217. The candidate lane-changing trajectory with the corresponding lane-changing time window is determined as the intermediate lane-changing trajectory.

[0106] Specifically, there will be a corresponding lane-changing time window, that is, the candidate lane-changing trajectory with the corresponding lane-changing time window will be determined as the intermediate lane-changing trajectory.

[0107] In this embodiment, a lane-changing time window corresponding to each candidate lane-changing trajectory is selected based on a first condition and a second condition. This lane-changing time window not only ensures that the current vehicle can completely execute the lane change when traveling according to the candidate lane-changing trajectory and the lane-changing time window, but also ensures that the current vehicle has no possibility of colliding with lane-changing obstacles during the lane-changing process. Simultaneously, by determining the lane-changing time window for each candidate lane-changing trajectory, a highly feasible lane-changing time is proposed. The lane-changing operation is then executed according to this time window, thus solving the problem in the prior art where the lane-changing opportunity must be abandoned when obstacles are present. This increases the probability of a successful lane change to a certain extent.

[0108] S218. If the lane change start times of the intermediate lane change trajectories are different, the intermediate lane change trajectory corresponding to the lane change time window whose lane change start time is closest to the current time shall be determined as the target lane change trajectory.

[0109] Specifically, when multiple intermediate lane-changing trajectories exist, the lane-changing start time of each intermediate lane-changing trajectory can be determined. If the lane-changing start times of the intermediate lane-changing trajectories are different, the intermediate lane-changing trajectory corresponding to the lane-changing time window whose lane-changing start time is closest to the current time can be determined as the target lane-changing trajectory.

[0110] S219. If the start time of the lane change in the intermediate lane change trajectory is the same, but the end time of the lane change is different, then the intermediate lane change trajectory corresponding to the lane change time window whose end time is farthest from the current time shall be determined as the target lane change trajectory.

[0111] Specifically, when multiple intermediate lane-changing trajectories exist, and the start time of the lane change is the same, the end time of the lane change for each intermediate lane-changing trajectories can be determined. If the end times of the intermediate lane-changing trajectories are different, the intermediate lane-changing trajectory corresponding to the lane-changing time window whose end time is furthest from the current time can be determined as the target lane-changing trajectory.

[0112] S220. If the start time of lane change of the intermediate lane change trajectories is the same and the end time of lane change of the intermediate lane change trajectories is the same, then the intermediate lane change trajectory with the longest driving distance within the lane change time window shall be determined as the target lane change trajectory.

[0113] Specifically, when there are multiple intermediate lane-changing trajectories, and the start and end times of the intermediate lane-changing trajectories are the same, the intermediate lane-changing trajectory with the longest current vehicle travel distance within the lane-changing time window can be used as the target lane-changing trajectory.

[0114] It is worth noting that S218, S219, and S220 can be parallel steps or progressive steps. That is, after executing S217, if there is more than one intermediate lane change trajectory, the optimal intermediate lane change trajectory can be obtained by filtering the intermediate lane change trajectories and used as the target lane change trajectory. For example, filtering the intermediate lane change trajectory is determined by comparing the lane change start time and lane change end time in the lane change time window corresponding to the intermediate lane change trajectory. In one case, when the lane change start times of more than one intermediate lane change trajectory are different, S218 can be executed; when the lane change start times of more than one intermediate lane change trajectory are the same but the lane change end times are different, S219 can be executed; when the lane change start times and lane change end times of more than one intermediate lane change trajectory are the same, S220 can be executed. In another scenario, all intermediate lane change trajectories are divided into two categories: the first category consists of intermediate lane change trajectories with different lane change start times, and the second category consists of intermediate lane change trajectories with the same lane change start time. The first category of intermediate lane change trajectories is processed by S218 to obtain the target lane change trajectory in S218. The second category of intermediate lane change trajectories is processed by S219 to obtain the target lane change trajectory in S219. If the target lane change trajectory is not unique at this point, the target lane change trajectory obtained in S218 and the target lane change trajectory obtained in S219 are used as new intermediate lane change trajectories, and S220 is executed to obtain the target lane change trajectory.

[0115] The order of execution of S218, S219 and S220 described above is merely an illustrative explanation and should not be construed as limiting the method of the present invention.

[0116] In this embodiment, by comparing the lane change start time, lane change end time and driving distance of each intermediate lane change trajectory's lane change time window, a preferred target lane change trajectory is selected from multiple intermediate lane change trajectories. This not only ensures the safety of lane changes and increases the probability of lane changes, but also improves the comfort of vehicle driving by selecting a preferred target lane change trajectory.

[0117] S221. Perform a lane change operation within the lane change time window of the target lane change trajectory.

[0118] Specifically, in practice, even after executing steps S218, S219, and S220, multiple preferred target lane-changing trajectories may still exist. At this point, the user can decide which target lane-changing trajectory to execute as the final target trajectory for this lane change. Simultaneously, once the target lane-changing trajectory is selected, the vehicle can begin the lane change according to the lane-changing time window corresponding to the target trajectory, starting at the lane-changing start time and continuing until the lane-changing end time is reached to complete the lane-changing operation.

[0119] In this embodiment, the lane-changing operation is performed according to the lane-changing time window of the target lane-changing trajectory, so that the vehicle performs the lane-changing operation according to the preferred lane-changing trajectory, thereby improving the user experience.

[0120] The lane-changing method provided by this invention first determines the required lane-changing trajectory control parameters based on user feedback and the current vehicle's computing power; it then determines the time and position information of the trajectory start point based on the current time and current driving position; finally, it determines the time interval between points based on the lane-changing trajectory duration and the number of lane-changing trajectory points in the lane-changing trajectory control parameters; starting from the trajectory start point, it determines the time information of the next candidate trajectory point based on the time information of the trajectory start point and the time interval between points; and it determines the position information from the previous candidate trajectory point to the current candidate trajectory point based on the comfort acceleration, comfort deceleration, or comfort driving speed and the time information of each candidate trajectory point; after determining all candidate trajectory points, at least one candidate lane change can be determined. The system identifies obstacles in the current lane and the lane-changing lane, defining them as lane-changing obstacles that may affect the vehicle's lane-changing operation. It then obtains the predicted trajectory of these obstacles. Using a first and second condition, it determines the lane-changing time window corresponding to each candidate lane-changing trajectory and obtains the determination result. Candidate lane-changing trajectories with corresponding time windows are designated as intermediate lane-changing trajectories. Based on the start time, end time, or travel distance of the intermediate lane-changing trajectory, a preferred target lane-changing trajectory is selected, and the lane-changing operation is performed according to the target trajectory's time window. In this technical solution, on the one hand, before calculating the automatic lane-changing trajectory, parameters for generating the automatic lane-changing trajectory are determined, namely, lane-changing trajectory control parameters. This provides a computational basis for the vehicle to generate a suitable and comfortable candidate lane-changing trajectory based on its own computing capabilities when generating the automatic lane-changing trajectory. On the other hand, each current candidate trajectory point can determine a first, second, or third driving distance based on the comfort acceleration, comfort deceleration, or comfort driving speed and the time information of the current candidate trajectory point. Furthermore, it can determine the first, second, or third position information corresponding to the current candidate trajectory point based on the position information of the previous candidate trajectory point and the first, second, or third driving distance. This allows for the determination of different current candidate trajectory points based on comfort acceleration, comfort deceleration, or comfort driving speed and other parameters, increasing the possibility of multiple lane-changing trajectories and thus increasing the probability of selecting a suitable lane-changing trajectory later. Additionally, by comparing the lane-changing start time, lane-changing end time, and driving distance within the lane-changing time window of each intermediate lane-changing trajectory, a preferred target lane-changing trajectory is selected from multiple intermediate lane-changing trajectories. This ensures lane-changing safety, increases the probability of lane-changing, and improves vehicle driving comfort by selecting the preferred target lane-changing trajectory. Finally, the lane-changing operation is executed according to the lane-changing time window of the target lane-changing trajectory, ensuring the vehicle follows the preferred lane-changing trajectory and enhancing the user experience.

[0121] Figure 4 This is a schematic diagram of the lane-changing device provided by the present invention. Figure 4 As shown, the device includes:

[0122] The first generation module 401 is used to determine the lane-changing trajectory control parameters of the current vehicle and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters.

[0123] Prediction module 402 is used to obtain the predicted driving trajectory of the current vehicle in the lane-changing obstacle;

[0124] The window determination module 403 is used to determine the lane change time window corresponding to each candidate lane change trajectory based on each candidate lane change trajectory and the predicted driving trajectory.

[0125] The second generation module 404 is used to determine the target lane change trajectory from at least one candidate lane change trajectory according to the lane change time window corresponding to each candidate lane change trajectory.

[0126] Execution module 405 is used to perform lane change operations within the lane change time window of the target lane change trajectory.

[0127] Optionally, the lane-changing trajectory control parameters of the current vehicle are determined. The first generation module 401 is specifically used for:

[0128] Determine the current vehicle's comfort acceleration, comfort deceleration, and comfort driving speed based on user feedback.

[0129] The duration of the lane-changing trajectory and the number of lane-changing trajectory points are determined based on the current computing power of the vehicle.

[0130] Comfort acceleration, comfort deceleration, comfort driving speed, lane change trajectory duration, and number of lane change trajectory points are used as lane change trajectory control parameters.

[0131] Optionally, at least one candidate lane-changing trajectory is generated based on the current driving position of the vehicle and the lane-changing trajectory control parameters. The first generation module 401 is specifically used for:

[0132] The time information of the trajectory start point is determined based on the current time, and the location information of the trajectory start point is determined based on the current driving position;

[0133] The time information of candidate trajectory points is determined based on the time information of the trajectory start point, the duration of the lane change trajectory, and the number of lane change trajectory points.

[0134] The location information of the candidate trajectory points is determined based on the location information of the trajectory start point, the comfort acceleration, the comfort deceleration, the comfort driving speed, and the time information of the candidate trajectory points.

[0135] At least one candidate lane-change trajectory is generated based on the time and location information of the trajectory start point and the time and location information of the candidate trajectory points.

[0136] Optionally, candidate trajectory points include the current candidate trajectory point and the previous candidate trajectory point, where the previous candidate trajectory point is either the trajectory start point or not. The time information of the candidate trajectory points is determined based on the time information of the trajectory start point, the duration of the lane-changing trajectory, and the number of lane-changing trajectory points. Specifically, the first generation module 401 is used for:

[0137] Obtain the time information of the previous candidate trajectory point;

[0138] The time interval between points is determined based on the duration of the lane change trajectory and the number of lane change trajectory points.

[0139] The time information of the current candidate trajectory point is determined based on the time information of the previous candidate trajectory point and the time interval between points.

[0140] Optionally, the position information of the candidate trajectory points is determined based on the position information of the trajectory starting point, comfort acceleration, comfort deceleration, comfort driving speed, and the time information of the candidate trajectory points. Specifically, the first generation module 401 is used for:

[0141] Determine the first travel distance obtained by driving according to the comfort acceleration and the time information of the current candidate trajectory point, and determine the first position information of the current candidate trajectory point based on the position information of the previous candidate trajectory point and the first travel distance;

[0142] Determine the second travel distance obtained by traveling according to the comfort deceleration and the time information of the current candidate trajectory point, and determine the second position information of the current candidate trajectory point based on the position information of the previous candidate trajectory point and the second travel distance;

[0143] The third driving distance is determined by driving at a comfortable speed and using the time information of the current candidate trajectory point. The third position information of the current candidate trajectory point is determined based on the position information of the previous candidate trajectory point and the third driving distance.

[0144] Optionally, at least one candidate lane-changing trajectory is generated based on the time and location information of the trajectory starting point, as well as the time and location information of the candidate trajectory points. The first generation module 401 is specifically used for:

[0145] At least one candidate lane-changing trajectory is generated based on the time and location information of the trajectory starting point, as well as the time, first location, second location, and third location information of the candidate trajectory points.

[0146] Optionally, the predicted trajectory of the current vehicle to lane-changing obstacles is obtained. The prediction module 402 is specifically used for:

[0147] Identify obstacles in the current lane and obstacles in the lane changing lane;

[0148] Obstacles in the forward lane and obstacles in the lane changing lane are identified as lane changing obstacles;

[0149] Obtain the predicted driving trajectory of lane-changing obstacles.

[0150] Optionally, a lane-changing time window corresponding to each candidate lane-changing trajectory is determined based on each candidate lane-changing trajectory and the predicted driving trajectory. The window determination module is specifically used for:

[0151] The time window that satisfies the first and second conditions is determined as the lane change time window corresponding to each candidate lane change trajectory.

[0152] The first condition is: within the lane-changing time window, there is no collision between the candidate lane-changing trajectory and the predicted driving trajectory;

[0153] The second condition is: the length of the lane-changing time window exceeds the preset duration.

[0154] Optionally, after determining the lane-changing time window corresponding to each candidate lane-changing trajectory based on each candidate lane-changing trajectory and the predicted driving trajectory, the window determination module 403 is further used for:

[0155] Obtain the determination result of the lane change time window corresponding to each candidate lane change trajectory. The determination result includes whether there is a corresponding lane change time window or not.

[0156] Candidate lane-changing trajectories with corresponding lane-changing time windows are identified as intermediate lane-changing trajectories.

[0157] Optionally, the target lane-changing trajectory is determined from at least one candidate lane-changing trajectory based on the lane-changing time window corresponding to each candidate lane-changing trajectory. The second generation module 404 is specifically used for:

[0158] The target lane change trajectory is determined from the lane change time window corresponding to the intermediate lane change trajectory.

[0159] Optionally, the lane-changing time window includes the lane-changing start time and lane-changing end time; the target lane-changing trajectory is determined from the intermediate lane-changing trajectory based on the lane-changing time window corresponding to the intermediate lane-changing trajectory. The second generation module 404 is specifically used for:

[0160] If the lane change start times of the intermediate lane change trajectories are different, the intermediate lane change trajectory corresponding to the lane change time window whose lane change start time is closest to the current time will be determined as the target lane change trajectory.

[0161] If the start times of lane changes in intermediate lane-changing trajectories are the same, but the end times of lane changes are different, then the intermediate lane-changing trajectory corresponding to the lane-changing time window whose end time is farthest from the current time will be determined as the target lane-changing trajectory.

[0162] If the start time and end time of the lane change trajectories in the middle lane change trajectory are the same, then the middle lane change trajectory with the longest driving distance within the lane change time window will be determined as the target lane change trajectory.

[0163] The lane-changing device provided in the embodiments of the present invention can execute the lane-changing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0164] Figure 5 This is a schematic diagram of the structure of a vehicle 5 provided for the present invention. The vehicle is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The vehicle can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0165] like Figure 5 As shown, vehicle 5 includes at least one processor 11 and a memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of vehicle 5. The processor 11, ROM 12, and RAM 13 are interconnected via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0166] Multiple components in vehicle 5 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows vehicle 5 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0167] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as lane-switching methods.

[0168] In some embodiments, the lane-changing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on vehicle 5 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lane-changing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the lane-changing method by any other suitable means (e.g., by means of firmware).

[0169] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, at least one input device, and at least one output device.

[0170] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0172] To provide interaction with the user, the systems and technologies described herein can be implemented in a vehicle having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0173] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0174] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0175] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0176] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A lane-changing method, characterized in that, include: Determine the lane-changing trajectory control parameters of the current vehicle, and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters; Obtain the predicted trajectory of the current vehicle from the lane-changing obstacle; The lane-changing time window corresponding to each candidate lane-changing trajectory is determined based on each candidate lane-changing trajectory and the predicted driving trajectory; The target lane change trajectory is determined from at least one of the candidate lane change trajectories based on the lane change time window corresponding to each candidate lane change trajectory. The lane change operation is performed within the lane change time window of the target lane change trajectory.

2. The lane-changing method according to claim 1, characterized in that, The determination of the lane-changing trajectory control parameters for the current vehicle includes: The comfort acceleration, comfort deceleration, and comfort driving speed of the current vehicle are determined based on user feedback. The duration of the lane-changing trajectory and the number of lane-changing trajectory points are determined based on the current vehicle's computing power. The comfort acceleration, the comfort deceleration, the comfort driving speed, the lane change trajectory duration, and the number of lane change trajectory points are used as the lane change trajectory control parameters.

3. The lane-changing method according to claim 2, characterized in that, The step of generating at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters includes: The time information of the trajectory start point is determined based on the current time, and the position information of the trajectory start point is determined based on the current driving position; The time information of the candidate trajectory points is determined based on the time information of the trajectory start point, the duration of the lane change trajectory, and the number of lane change trajectory points. The position information of the candidate trajectory point is determined based on the position information of the trajectory starting point, the comfort acceleration, the comfort deceleration, the comfort driving speed, and the time information of the candidate trajectory point; At least one candidate lane-changing trajectory is generated based on the time and location information of the trajectory starting point and the time and location information of the candidate trajectory points.

4. The lane-changing method according to claim 3, characterized in that, The candidate trajectory point includes the current candidate trajectory point and the previous candidate trajectory point of the current candidate trajectory point. The previous candidate trajectory point is the trajectory starting point, or the previous candidate trajectory point is not the trajectory starting point. The step of determining the time information of candidate trajectory points based on the time information of the trajectory start point, the duration of the lane change trajectory, and the number of lane change trajectory points includes: Obtain the time information of the previous candidate trajectory point; The time interval between points is determined based on the duration of the lane-changing trajectory and the number of points on the lane-changing trajectory. The time information of the current candidate trajectory point is determined based on the time information of the previous candidate trajectory point and the time interval between points.

5. The lane-changing method according to claim 4, characterized in that, The step of determining the position information of the candidate trajectory point based on the position information of the trajectory starting point, the comfort acceleration, the comfort deceleration, the comfort driving speed, and the time information of the candidate trajectory point includes: Determine the first travel distance obtained by traveling according to the comfort acceleration and the time information of the current candidate trajectory point, and determine the first position information of the current candidate trajectory point according to the position information of the previous candidate trajectory point and the first travel distance; Determine the second travel distance obtained by traveling according to the comfort deceleration and the time information of the current candidate trajectory point, and determine the second position information of the current candidate trajectory point according to the position information of the previous candidate trajectory point and the second travel distance; The third driving distance is determined by driving at the comfortable driving speed and the time information of the current candidate trajectory point, and the third position information of the current candidate trajectory point is determined based on the position information of the previous candidate trajectory point and the third driving distance.

6. The lane-changing method according to claim 5, characterized in that, The step of generating at least one candidate lane-changing trajectory based on the time and location information of the trajectory starting point and the time and location information of the candidate trajectory points includes: At least one candidate lane-changing trajectory is generated based on the time and location information of the trajectory starting point, as well as the time, first location, second location, and third location information of the candidate trajectory points.

7. The lane-changing method according to claim 1, characterized in that, The step of obtaining the predicted driving trajectory of the current vehicle to the lane-changing obstacle includes: Identify obstacles in the current lane and obstacles in the lane changing lane; The obstacle in the current lane and the obstacle in the lane-changing lane are identified as the lane-changing obstacle; Obtain the predicted trajectory of the lane-changing obstacle.

8. The lane-changing method according to claim 7, characterized in that, The step of determining the lane-changing time window corresponding to each candidate lane-changing trajectory based on each candidate lane-changing trajectory and the predicted driving trajectory includes: The time window that satisfies the first and second conditions is determined as the lane change time window corresponding to each of the candidate lane change trajectories. The first condition is: within the lane-changing time window, the candidate lane-changing trajectory does not collide with the predicted driving trajectory; The second condition is that the length of the lane-changing time window exceeds the preset duration.

9. The lane-changing method according to claim 1, characterized in that, After determining the lane-changing time window corresponding to each candidate lane-changing trajectory based on each candidate lane-changing trajectory and the predicted driving trajectory, the method further includes: Obtain the determination result of the lane change time window corresponding to each of the candidate lane change trajectories, the determination result including whether there is a corresponding lane change time window and whether there is no corresponding lane change time window; Candidate lane-change trajectories with corresponding lane-change time windows are identified as intermediate lane-change trajectories. The step of determining the target lane change trajectory from at least one candidate lane change trajectory based on the lane change time window corresponding to each candidate lane change trajectory includes: The target lane change trajectory is determined from the intermediate lane change trajectory based on the lane change time window corresponding to the intermediate lane change trajectory.

10. The lane-changing method according to claim 9, characterized in that, The lane-changing time window includes the lane-changing start time and lane-changing end time. Determining the target lane-changing trajectory from the intermediate lane-changing trajectory based on the lane-changing time window corresponding to the intermediate lane-changing trajectory includes: If the lane change start times of the intermediate lane change trajectories are different, then the intermediate lane change trajectory corresponding to the lane change time window whose lane change start time is closest to the current time is determined as the target lane change trajectory. If the start times of the intermediate lane-changing trajectories are the same, but the end times of the intermediate lane-changing trajectories are different, then the intermediate lane-changing trajectory corresponding to the lane-changing time window whose end time is farthest from the current time is determined as the target lane-changing trajectory. If the start time and end time of the intermediate lane-changing trajectories are the same, then the intermediate lane-changing trajectory with the longest driving distance within the lane-changing time window is determined as the target lane-changing trajectory.

11. A lane-changing device, characterized in that, include: The first generation module is used to determine the lane-changing trajectory control parameters of the current vehicle and generate at least one candidate lane-changing trajectory based on the current driving position of the current vehicle and the lane-changing trajectory control parameters. The prediction module is used to obtain the predicted driving trajectory of the current vehicle in the lane-changing obstacle; The window determination module is used to determine the lane change time window corresponding to each candidate lane change trajectory based on each candidate lane change trajectory and the predicted driving trajectory; The second generation module is used to determine the target lane change trajectory from at least one of the candidate lane change trajectories based on the lane change time window corresponding to each candidate lane change trajectory. The execution module is used to perform a lane change operation within the lane change time window of the target lane change trajectory.

12. A vehicle, characterized in that, include: One or more processors; Memory, used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the lane-changing method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the lane-switching method according to any one of claims 1-10.

Images